Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and does substantial work: it discloses that entitlements not applicable to a path are skipped with a reason rather than summed, that the result is decomposed by origin, and that the tool only measures runway and does not make the decision for the user. It could add more about tax handling or whether the current reserve is included, but the core behavioral traits are clearly stated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the main verb and purpose, and every sentence adds value: the first defines scope and outputs, the second explains the skip-with-reason behavior, and the third clarifies the tool's non-decisional stance. The only minor flaw is the dense, single-sentence enumeration with heavy parentheticals and the stylized 'POR ORIGEM', which makes it slightly harder to parse than necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 10 parameters, no annotations, and no output schema, the description provides a solid conceptual picture: what is calculated, how unavailable benefits are treated, and what the result means (runway). It does not explicitly explain how parameters like dependents, works_notice, or security_target_months affect the result, but the schema covers those details well enough that the agent can still select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents all 10 parameters with 100% coverage, including ranges and defaults, so the description need not repeat them. The description adds no direct parameter-level detail, but its explanation of the output decomposition (FGTS sacável, caixa total por origem, runway) indirectly clarifies why parameters like fgts_balance and monthly_expenses matter. This aligns with the baseline 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Quantifica') and a precise resource ('a consequência financeira de sair do emprego CLT hoje'), then enumerates the outputs: liquid severance, withdrawable FGTS, unemployment insurance when applicable, total cash by source, and runway in months. This distinguishes it from sibling calculators like calculate_severance or calculate_unemployment_insurance by framing it as a holistic quit-decision tool rather than a single-component calculation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The use case is strongly implied: it is for someone considering leaving a CLT job today, choosing among resignation, mutual agreement, or dismissal without cause. However, there is no explicit guidance about when to choose this tool over closely related siblings such as calculate_severance, check_severance, or compare_clt_vs_pj, so the agent must infer the boundary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.